· Segmentation of cardiovascular structures
· Visualization and image reconstruction techniques: 2D review, Volume Rendering, MPR
· Simulation of TEE views, ICE views, and fluoroscopic rendering
· Measurement and annotation tools
· Reporting tools

TruPlan's intended patient population is comprised of adult patients.

Device Description

The TruPlan Computed Tomography (CT) Imaging Software application ("TruPlan") is a software as a medical device that helps qualified users with image-based pre-procedural planning and post-procedural follow-up of the Left Atrial Appendage Closure (LAAC) procedure using CT data. TruPlan is designed to support the anatomical assessment of the Left Atrial Appendage (LAA) prior to and following the LAAC procedure. This includes the assessment of the LAA size, shape, and relationships with adjacent cardiac and extracardiac structures. This assessment helps the physician determine the size of a closure device needed for the LAAC procedure and evaluate LAAC device placement in a follow-up CT study. The TruPlan application is a visualization software and has basic measurement tools. The device is intended to be used as an aid to the existing standard of care and does not replace existing software applications physicians use for planning or follow-up for a LAAC procedure.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) submission for TruPlan Computed Tomography (CT) Imaging Software:

Acceptance Criteria and Device Performance Study for TruPlan CT Imaging Software

The TruPlan Computed Tomography (CT) Imaging Software by Circle Cardiovascular Imaging, Inc. underwent validation of its machine learning (ML) derived outputs to demonstrate its performance relative to pre-defined acceptance criteria. The device contains two primary ML algorithms: Left Heart Segmentation and Landing Zone Detection.

1. Table of Acceptance Criteria and Reported Device Performance

Feature / Metric	Acceptance Criteria (Pre-defined)	Reported Device Performance
Left Heart Segmentation Algorithm
Probability of Bone Removal (Segmentation Accuracy)	Not explicitly stated as a numerical threshold, but implied to be high for correct segmentation.	532/533 cases (99.81%) for bone removal
Probability of LAA Visualization (Segmentation Accuracy)	Not explicitly stated as a numerical threshold, but implied to be high for correct visualization.	519/533 cases (97.37%) for LAA visualization
Landing Zone Detection Algorithm
Landing Zone Plane Distance Metric	Within 10 mm	97/100 cases (97%) within 10 mm (mean distance: 3.87 mm)
Landing Zone Contour Center Distance Metric	Within 12 mm	99/100 cases (99%) within 12 mm (mean distance: 2.92 mm)

Note: The document states that "All performance testing results met Circle's pre-defined acceptance criteria," indicating that the reported performance metrics met or exceeded the internal thresholds established by the manufacturer, even if the exact numerical acceptance percentages for segmentation accuracy were not explicitly listed as criteria in the provided text.

2. Sample Sizes Used for the Test Set and Data Provenance

Test Set Sample Size:
- Left Heart Segmentation: 533 anonymized patient images
- Landing Zone Detection: 100 anonymized patient images
Data Provenance:
- Country of Origin: The validation data was sourced from multiple sites across the U.S. and other urban regions. Specifically:
  - Left Heart Segmentation: U.S., Canada, South America, Europe, and Asia.
  - Landing Zone Detection: Various sites across the U.S.
- Retrospective/Prospective: The data used for validation were pre-existing CT images, common for retrospective studies. The document states "All data used for validation were not used during the development of the training algorithms," ensuring independence.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

The document mentions that for the Landing Zone Detection algorithm, "The landing zone was manually contoured by multiple expert readers for evaluation."

For the training data of the Left Heart Segmentation algorithm, it states "the left heart structures were manually annotated by multiple expert readers." While this refers to training, it implies a similar process and expert qualification for testing.

The specific number of experts and their explicit qualifications (e.g., "radiologist with 10 years of experience") are not specified in the provided text for either training or validation ground truth establishment. It only states "expert readers."

4. Adjudication Method for the Test Set

The document indicates that for the Landing Zone Detection ground truth, the "landing zone was manually contoured by multiple expert readers." For the Left Heart Segmentation training data, "manually annotated by multiple expert readers." This implies a consensus or majority vote approach might have been used, but the specific adjudication method (e.g., 2+1, 3+1, none) is not explicitly detailed in the provided text.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

No, a MRMC comparative effectiveness study was not done. The document explicitly states: "No clinical studies were necessary to support substantial equivalence." The performance data presented is that of the algorithm's standalone performance against expert-defined ground truth, rather than a comparison of human readers with and without AI assistance. Therefore, an effect size of human reader improvement with AI vs. without AI assistance is not provided and was not part of this submission.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, standalone performance was evaluated. The metrics reported (Probability of Bone Removal, Probability of LAA Visualization, Landing Zone Plane Distance, Landing Zone Contour Center Distance) are direct measurements of how accurately the ML algorithms perform their specific tasks when processing the CT images. The "Validation of Machine Learning Derived Outputs" section focuses purely on the algorithm's performance against ground truth.

7. The Type of Ground Truth Used

The ground truth used was expert consensus/manual contouring/annotation.

For Left Heart Segmentation: "left heart structures were manually annotated by multiple expert readers."
For Landing Zone Detection: "the landing zone was manually contoured by multiple expert readers."

This is observational data interpreted by human experts, not pathology or outcomes data.

8. The Sample Size for the Training Set

Left Heart Segmentation: 113 cases
Landing Zone Detection: 273 cases

9. How the Ground Truth for the Training Set Was Established

Left Heart Segmentation: "the left heart structures were manually annotated by multiple expert readers."
Landing Zone Detection: "the landing zone was manually contoured by expert readers."

Similar to the test set, the ground truth for training was established through manual annotation and contouring by expert readers. The document emphasizes that "the separation into training versus validation datasets is made on the study level to ensure no overlap between the two sets."

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Circle Cardiovascular Imaging, Inc. % Sydney Toutant Regulatory Affairs Lead Suite 1100 - 800 5th Ave. SW Calgary, Alberta T2P 3T6 CANADA

January 18, 2023

Re: K222593

Trade/Device Name: TruPlan Computed Tomography (CT) Imaging Software Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QIH, LLZ Dated: December 9, 2022 Received: December 9, 2022

Dear Sydney Toutant:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for

{1}------------------------------------------------

devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely.

Jessica Lamb

Jessica Lamb, Ph.D. Assistant Director Imaging Software DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K222593

Device Name

TruPlan Computed Tomography (CT) Imaging Software

Indications for Use (Describe)

TruPlan enables visualization and measurement of structures of the heart and vessels for:

· Pre-procedural planning and sizing for the left atrial appendage closure (LAAC) procedure
· Post-procedural evaluation for the LAAC procedure

To facilitate the above, TruPlan provides general functionality such as:

· Segmentation of cardiovascular structures
· Visualization and image reconstruction techniques: 2D review, Volume Rendering, MPR
· Simulation of TEE views, ICE views, and fluoroscopic rendering
· Measurement and annotation tools
· Reporting tools

TruPlan's intended patient population is comprised of adult patients.

Type of Use (Select one or both, as applicable)
-------------------------------------------------

X Prescription Use (Part 21 CFR 801 Subpart D)

| Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

Image /page/3/Picture/1 description: The image contains the logo for Circle Cardiovascular Imaging. The logo features two incomplete circles, one larger and green, and one smaller and yellow, positioned above the word "circle" in gray lowercase letters. Below "circle" are the words "CARDIOVASCULAR IMAGING" in smaller, uppercase gray letters. The overall design is clean and professional, suggesting a focus on medical imaging technology.

The following 510(k) summary of safety and effectiveness information is submitted in accordance with the requirements of the Safe Medical Device Act 1990 and 21 CFR 807.92(c).

l. SUBMITTER

Submitter's Name:	Circle Cardiovascular Imaging, Inc.
Address:	Suite 1100 – 800 5th Ave SW, Calgary, AB, Canada, T2P 3T6
Date Prepared:	January 16 2023
Telephone Number:	+1 587 747 4692
Contact Person :	Sydney Toutant
Email:	sydney.toutant@circlecvi.com

II. DEVICE

Name of the Device:	TruPlan Computed Tomography (CT) Imaging Software
Short Brand Name:	TruPlan
Common or Usual Name:	Automated Radiological Image Processing System
Classification Name:	Medical image management and processing system
Proposed Classification:	Device Class: II
	Primary Product Code: QIH
	Secondary Product Code: LLZ
	Regulation Number: 21 CFR 892.2050

PREDICATE DEVICES lll.

The primary predicate is the previously cleared version of TruPlan, manufactured by Circle CVI and cleared under K202212. 3mensio Workstation, manufactured by Pie Medical Imaging and cleared under K153736, is used as a secondary predicate.

The predicate devices have not been subject to a design-related recall.

{4}------------------------------------------------

IV. DEVICE DESCRIPTION

Pre-existing CT images are uploaded in TruPlan manually by the end-user. The images can be viewed by the user in the original CT image as well as simulated views. The software displays the views in a modular format as follows:

Left Atrial Appendage (LAA) .
Fluoroscopy (Fluoro, simulation) ●
Trans Esophageal Echo (TEE, simulation) ●
Intra Cardiac Echography (ICE, simulation) ●
. Thrombus
Follow-up
Multiplanar Reconstruction (MPR)
Reporting ●

These views offer the user visualization and quantification capabilities for pre-procedural planning and post-procedural follow-up of the LAAC procedure; none are intended for diagnosis. The quantification tools are based on user-identified regions of interest and are user-modifiable. The device allows users to perform the measurements (all done on MPR viewers) listed in Table 1, below.

TruPlan implements machine learning techniques to aid device use as follows:

1. Left Heart Segmentation. TruPlan generates a 3D rendering of the left side of the heart (including left ventricle, left atrium, and LAA) using machine learning methodology. The 3D rendering is for visualization purposes only; no measurement or annotations can be done using this view.
1. Landing Zone Detection. TruPlan uses machine learning techniques to initialize landing zone detection. No measurements are computed until the user reviews and corrects this initialization.

The data used to train TruPlan's machine learning algorithms were sourced from multiple clinical sites from urban centers and from different countries. The Left Heart Segmentation algorithm was trained on a total of 113 cases from the U.S., Canada, Germany, and other locations acquired using Siemens, GE, Toshiba, and Philips scanners where the left heart structures were manually

Circle Cardiovascular Imaging Inc.

{5}------------------------------------------------

annotated by multiple expert readers. The Landing Zone Detection algorithm was trained on a total of 273 cases from various sites across the U.S. acquired using Siemens, GE, Toshiba, and Philips scanners where the landing zone was manually contoured by expert readers.

When selecting data for training, the importance of model generalization was considered and data was selected such that a good distribution of patient demographics, scanner, and image parameters were represented. The separation into training versus validation datasets is made on the study level to ensure no overlap between the two sets. As such, different scans from the same study were not split between the training and validation datasets. None of the cases used for model validation were used for training the machine learning models.

Table 1. TruPlan's measurement functionality and the specific module/workflow and measurement application for which it is used.

Measurement [units]	Description	Module / Workflow	Application
Distance [mm]	Length between two points,for both curved lines(splines) and straight lines,including the diameter(including min, max,average) resulting fromclosed splines and depth ofthe LAA	All modules	Diameter & depth of LAAlanding zone (LAA module);distance between points ofinterest; diameter of a peri-device leak (Follow-upmodule)
Perimeter [mm]	The perimeter of a contour(closed spline)	All modules	Perimeter of LAA landing zone(LAA module); perimeter ofother contours of interest
Area [mm²]	The area within a contour	All modules	Area of LAA landing zone(LAA module); area of othercontoursof interest
Angle [degrees]	The angle of an object /structure of interest	All modules	Angle between two lines ofinterest
Signal intensity[HU]	Hounsfield value (inHounsfield Units, HU) of theunderlying pixels	All modules	Signal intensity of pixels in theregular vs. delayed scan(Thrombus module); averagesignal intensity within distalLAA (Follow-up module);intensity of other pixels ofinterest
Coordinates[mm, mm, mm]	Location in the x-, y-, and z-planes of a point	All modules	Coordinates of points ofinterest on a 3D rendering,for export purposes

{6}------------------------------------------------

These measurements are all manually placed by the user as annotations (overlays) and report the information calculated using the underlying pixels. TruPlan also provides reporting functionality to capture screenshots and measurements and to store them as a PDF document.

TruPlan is installed either as a standalone software onto the user's desktop or laptop computer, or as a server within the hospital infrastructure with a thick-client software on multiple users' desktop or laptop computers.

V. INDICATIONS FOR USE

TruPlan enables visualization and measurement of structures of the heart and vessels for:

Pre-procedural planning and sizing for the left atrial appendage closure (LAAC) . procedure
Post-procedural evaluation for the LAAC procedure

To facilitate the above, TruPlan provides general functionality such as:

Segmentation of cardiovascular structures ●
. Visualization and image reconstruction techniques: 2D review, Volume Rendering, MPR
Simulation of TEE views, ICE views, and fluoroscopic rendering ●
Measurement and annotation tools
Reporting tools ●

TruPlan's intended patient population is comprised of adult patients.

Image /page/6/Picture/14 description: The image shows a yellow warning sign. The sign is in the shape of a triangle with a thick black border. Inside the triangle is a large black exclamation point.

IMPORTANT: TruPlan is intended to be used as a pre-procedural planning aid, and LAAC procedures should be performed per the chosen LAAC device's approved IFU.

Image /page/6/Picture/16 description: The image shows a yellow triangle with a black exclamation point inside. The triangle is a warning sign, indicating a potential hazard or danger. The exclamation point emphasizes the importance of the warning. The sign is commonly used to alert people to be cautious and pay attention to their surroundings.

IMPORTANT: TruPlan is intended to be used as a post-procedural assessment aid, and all clinical decisions should be made per the chosen LAAC device's approved IFU.

{7}------------------------------------------------

VI. COMPARISON WITH PREDICATE DEVICES

The detailed analysis of the subject device and the primary and secondary predicate devices (shown in Table 2 and Table 3) demonstrates that the subject device is substantially equivalent in indications for use / intended use, technological characteristics, functionality, and operating principles with the primary predicate (K202212) and with the secondary predicate (K153736). Of the three characteristics (technical, biological, and clinical) required for the demonstration of equivalence, biological characteristics are not applicable since the subject device and both predicate devices are software as a medical device application with no tangible component interfacing with the body.

Subject Device	Primary Predicate	Secondary Predicate
TruPlan v3.0 (K222593)	TruPlan v1.0 (K202212)	3mensio (K153736)
Manufactured by Circle	Manufactured by Circle	Manufactured by Pie Medical Imaging
TruPlan enables visualization andmeasurement of structures of the heartand vessels for:	TruPlan enables visualization andmeasurement of structures of the heartand vessels for pre-procedural planningand sizing for the left atrial appendageclosure (LAAC) procedure.	3mensio Workstation enables visualizationand measurement of structures of theheart and vessels for:
• Pre-procedural planning and sizing forthe left atrial appendage closure(LAAC) procedure	To facilitate the above, TruPlan providesgeneral functionality such as:	• Pre-operational planning and sizingfor cardiovascular interventions andsurgery
• Post-procedural evaluation for theLAAC procedure	• Segmentation of cardiovascularstructures	• Postoperative evaluation
To facilitate the above, TruPlan providesgeneral functionality such as:	• Visualization and imagereconstruction techniques: 2D review,Volume Rendering, MPR	• Support of clinical diagnosis byquantifying dimensions in coronaryarteries
• Segmentation of cardiovascularstructures	• Simulation of TEE views, ICE views,and fluoroscopic rendering	• Support of clinical diagnosis byquantifying calcifications (calciumscoring) in the coronary arteries
• Visualization and imagereconstruction techniques: 2D review,Volume Rendering, MPR	• Measurement and annotation tools	To facilitate the above, 3mensioWorkstation provides general functionalitysuch as:
• Simulation of TEE views, ICE views,and fluoroscopic rendering	• Reporting tools	• Segmentation of cardiovascularstructures
• Measurement and annotation tools	TruPlan's intended patient population iscomprised of adult patients.	• Automatic and manual centerlinedetection
• Reporting tools		• Visualization and imagereconstruction techniques: 2D review,Volume Rendering, MPR, CurvedMPR, Stretched CMPR, Slabbing,MIP, AIP, MinIP
TruPlan's intended patient population iscomprised of adult patients.		• Measurement and annotation tools
		• Reporting tools

	Table 2. Indications for Use comparison to predicate devices.


Feature	Subject Device	Primary Predicate	Secondary Predicate
	TruPlan v3.0 (K222593)	TruPlan v1.0 (K202212)	3mensio (K153736)
	Manufactured by Circle	Manufactured by Circle	Manufactured by Pie Medical
Device Class	II	II	II
Device Classification	QIHLLZ	LLZ	LLZ
Regulation Name	Medical image management andprocessing system	Picture Archiving andCommunications System	Picture Archiving andCommunications System
Regulation Number	21 CFR 892.2050	21 CFR 892.2050	21 CFR 892.2050
Input data type	CT data in DICOM format (vendorindependent)	CT data in DICOM format (vendorindependent)	CT data in DICOM (vendorindependent)
Landing ZoneDetection	Semi-automatic initialization of thelanding zone using MachineLearning techniques; manualconfirmation of the landing zone	Manual initialization andconfirmation of the landing zone	Manual initialization andconfirmation of the landing zone
Left HeartSegmentation	Semi-automatic segmentation for3D visualization of the left heartusing Machine Learningtechniques; manual editing of 3Dviews possible	Semi-automatic segmentation for3D visualization of the left heartusing Machine Learningtechniques; manual editing of 3Dviews possible	Semi-automatic segmentation for3D visualization of the left heart;manual editing of 3D views possible
Study list imagefunctionality	Study/series previewing Exporting Deleting Anonymizing Search	Study/series previewing Exporting Deleting Anonymizing Search	Study/series previewing Exporting Deleting Anonymizing Search
Image assessment –simulated views	Fluoroscopy (grayscale 3Drendering), to visualizerelationship among LAACprocedure relevantanatomical structures TEE, to provide similar viewsto intraprocedural TEE ICE, to provide similar viewsto intraprocedural ICE	Fluoroscopy (grayscale 3Drendering), to visualizerelationship among LAACprocedure relevantanatomical structures TEE, to provide similar viewsto intraprocedural TEE ICE, to provide similar viewsto intraprocedural ICE	Grayscale 3D rendering, tovisualize relationship amongLAAC procedure relevantanatomical structures TEE, to provide similar views tointraprocedural TEE
Image assessment –other visualizationfunctionality	2D 3D (with manual & semi-automatic segmentation) 4D (cine) MPR Annotations	2D 3D (with manual & semi-automatic segmentation) 4D (cine) MPR Annotations	2D 3D (with manual & semi-automatic segmentation) 4D (cine) MPR Annotations Curved MPR Stretch CMPR Slabbing MIP AIP MinIP Centreline extraction Calcium coring
Image assessment –measurementfunctionality	Distance (length, diameter,perimeter) Area Angle Signal intensity Coordinates	Distance (length, diameter,perimeter) Area Angle Signal intensity Coordinates	Distance (length, diameter,perimeter) Area Angle Signal intensity Coordinates Volume
Report functionality	Patient/study information	Patient/study information	Patient/study information
Feature	Subject Device	Primary Predicate	Secondary Predicate
	TruPlan v3.0 (K222593)	TruPlan v1.0 (K202212)	3mensio (K153736)
	Manufactured by Circle	Manufactured by Circle	Manufactured by Pie Medical
	Screenshots	Screenshots	Screenshots
	●	●	●
	Measurements	Measurements	Measurements
	●	●	●
	Free text	Free text	Free text
	●	●	●
	Device sizing table (for	Device sizing table (for	Device-specific reports for
	reference only) for LAA	reference only) for LAA	procedures covered in intended
	procedure	procedure	use
Operating system	Microsoft WindowsApple macOS	Microsoft Windows	Microsoft Windows
DICOM compliant	Yes	Yes	Yes

{8}------------------------------------------------

Table 3. Feature comparison to primary and secondary predicate devices.

Circle Cardiovascular Imaging Inc.

Non-Confidential

{9}------------------------------------------------

VII. PERFORMANCE DATA AND TESTING

Performance testing was conducted to verify compliance with specified design requirements in accordance with ISO 13485:2016, IEC 62304:2015, ISO 14971:2019, and NEMA 3.1-3.20 (2016) DICOM standards.

Verification and validation testing were conducted to ensure specifications and performance of the device and were performed per the FDA Guidance documents "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" and "Content of Premarket Submission for Management of Cybersecurity in Medical Devices". No clinical studies were necessary to support substantial equivalence.

TruPlan has been tested according to the specifications that are documented in a Master Software Test Plan. Testing is an integral part of Circle Cardiovascular Imaging Inc.'s software development as described in the company's product development process.

Validation of Machine Learning Derived Outputs

The machine learning algorithms of TruPlan (left heart segmentation, landing zone detection) have been trained and tested on images acquired from major vendors of CT imaging devices. All data used for validation were not used during the development of the training algorithms.

Across all CT machine manufacturers, n = 633 anonymized patient images were used for the validation of TruPlan. This translates into 533 samples (age and sex information unknown due to anonymization) for Left Heart Segmentation, and 100 samples (59 male and 41 female samples acquired from patients between 56 to 90+ years of age) for Landing Zone Detection. Image information for all samples was anonymized and limited to ePHI-free DICOM headers. The validation data was sourced from multiple sites across the U.S. and other urban regions. All performance testing results met Circle's pre-defined acceptance criteria.

. For the Left Heart Segmentation algorithm, the performance acceptance criteria were predefined to evaluate the performance of the ML model based on seqmentation accuracy defined by probability of bone removal and probability of LAA visualization. The validation data was collected from the U.S., Canada, South America, Europe, and Asia acquired

{10}------------------------------------------------

using Siemens, GE, Toshiba, and Philips scanners. Bone was removed in 532/533 cases (99.81%); the LAA was correctly visualized by the rendering algorithm in 519/533 cases (97.37%).

For the Landing Zone Detection algorithm, the performance acceptance criteria were pre-. defined to evaluate the performance of the ML model based on detection accuracy defined by plane and contour center distance. The validation data was collected from various sites across the U.S., acquired using Siemens, GE, Toshiba, and Philips scanners. The landing zone was manually contoured by multiple expert readers for evaluation. Landing zone plane distance was within 10 mm in 97/100 cases (97%) with a mean distance of 3.87 mm; the landing zone contour center distance was within 12 mm in 99/100 cases (99%) with a mean distance of 2.92 mm.

VIII. CONCLUSIONS

The information submitted in this premarket notification, including the performance testing and predicate device comparisons, support the safety and effectiveness of TruPlan as compared to the predicate devices when used for the defined intended use.

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).